Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

657
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
657

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Bridging Domain Gaps in Computational Pathology: A Comparative Study of Adaptation Strategies.

Sensors (Basel, Switzerland)·2025
Same author

Comprehensive Review: Machine and Deep Learning in Brain Stroke Diagnosis.

Sensors (Basel, Switzerland)·2024
Same author

Author Correction: An interpretable machine learning system for colorectal cancer diagnosis from pathology slides.

NPJ precision oncology·2024
Same author

An interpretable machine learning system for colorectal cancer diagnosis from pathology slides.

NPJ precision oncology·2024
Same author

Classification of Pulmonary Nodules in 2-[<sup>18</sup>F]FDG PET/CT Images with a 3D Convolutional Neural Network.

Nuclear medicine and molecular imaging·2024
Same author

BOLD: Blood-gas and Oximetry Linked Dataset - Open Source Research.

medRxiv : the preprint server for health sciences·2023

相关实验视频

Updated: Jul 5, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K

解释深层物体探测器中的边界盒,使用自动驾驶系统的后 hoc 方法.

Caio Nogueira1, Luís Fernandes1,2, João N D Fernandes1,2

  • 1Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal.

Sensors (Basel, Switzerland)
|January 23, 2024
PubMed
概括

像D-RISE这样的可解释人工智能 (XAI) 方法为自动驾驶物体检测的深度学习模型提供了更多人能理解的见解,提高了信任和透明度.

关键词:
自动驾驶自动驾驶的自动驾驶.可以解释的人工智能AI对象检测检测对象检测对象检测

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

556

相关实验视频

Last Updated: Jul 5, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

556

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 自主系统 自主系统

背景情况:

  • 深度学习模型对于自动驾驶感知任务,如对象检测至关重要.
  • 这些模型的"黑子"性质需要安全性和可靠性的解释性.
  • 现有的可解释的人工智能 (XAI) 技术需要在复杂的自动驾驶环境中进行彻底评估.

研究的目的:

  • 探索和比较可解释的AI (XAI) 技术,用于自动驾驶中的物体检测.
  • 评估基于梯度和基于扰动的突出度方法,包括D-RISE.
  • 分析不同骨干架构和数据集对解释质量的影响.

主要方法:

  • 基于梯度 (例如,指导反向传播) 和基于干扰 (例如,D-RISE) 的突出性方法的比较.
  • 广泛的实验使用不同的骨干架构和数据集.
  • 视觉解释和解释方法的数值评估.

主要成果:

  • 无论是D-RISE还是指导反向传播,都产生了局部化的解释.
  • D-RISE突出了更多具有语义意义的区域,导致了更多人类可以理解的解释.
  • 这项研究是第一个针对对象检测的边界框坐标回归的解释.

结论:

  • 与其他经过测试的突出性方法相比,D-RISE为自动驾驶物体检测提供了更优质,人类可以理解的解释.
  • 可解释性AI (XAI) 对于建立对安全关键应用程序 (如自动驾驶) 深度学习模型的信任至关重要.
  • 进一步研究XAI用于自动驾驶中的回归任务是有必要的.